feat: enhance chat service with documentation indexing and improved Docker configuration

scripts/index_docs.py

@@ -0,0 +1,90 @@
+#!/usr/bin/env python3
+"""
+Script to index documentation into ChromaDB vector store.
+This script should be run once to initialize the documentation search capability.
+"""
+
+import asyncio
+import logging
+import sys
+from pathlib import Path
+
+# Add src to path
+sys.path.insert(0, str(Path(__file__).parent.parent / "src"))
+
+from datacenter_docs.chat.agent import DocumentationAgent
+
+logging.basicConfig(
+    level=logging.INFO,
+    format="%(asctime)s - %(name)s - %(levelname)s - %(message)s"
+)
+logger = logging.getLogger(__name__)
+
+
+async def main() -> None:
+    """Index all documentation files into vector store."""
+
+    # Paths
+    docs_path = Path("/app/output")  # In Docker container
+    if not docs_path.exists():
+        # Fallback to local path
+        docs_path = Path(__file__).parent.parent / "output"
+
+    vector_store_path = Path("/app/data/chroma_db")  # In Docker container
+    if not vector_store_path.parent.exists():
+        # Fallback to local path
+        vector_store_path = Path(__file__).parent.parent / "data" / "chroma_db"
+
+    logger.info(f"Indexing documentation from: {docs_path}")
+    logger.info(f"Vector store location: {vector_store_path}")
+
+    # Check if docs exist
+    md_files = list(docs_path.glob("**/*.md"))
+    if not md_files:
+        logger.warning(f"No markdown files found in {docs_path}")
+        logger.info("Creating sample documentation...")
+        # Could optionally create sample docs here
+        return
+
+    logger.info(f"Found {len(md_files)} markdown files to index")
+
+    try:
+        # Initialize agent (without MCP client for indexing only)
+        logger.info("Initializing Documentation Agent...")
+        agent = DocumentationAgent(
+            mcp_client=None,
+            llm_client=None,
+            vector_store_path=str(vector_store_path)
+        )
+
+        # Index documentation
+        logger.info("Starting indexing process...")
+        await agent.index_documentation(docs_path)
+
+        logger.info("✓ Documentation indexed successfully!")
+        logger.info(f"Vector store saved to: {vector_store_path}")
+
+        # Test search
+        logger.info("\nTesting search functionality...")
+        test_queries = [
+            "How to troubleshoot VLAN connectivity?",
+            "What are the backup schedules?",
+            "How to check UPS status?"
+        ]
+
+        for query in test_queries:
+            results = await agent.search_documentation(query, limit=2)
+            logger.info(f"\nQuery: {query}")
+            logger.info(f"Found {len(results)} results:")
+            for i, result in enumerate(results, 1):
+                logger.info(f"  {i}. {result['section']} (score: {result['relevance_score']:.2f})")
+
+        logger.info("\n✓ Indexing and testing complete!")
+
+    except Exception as e:
+        logger.error(f"Failed to index documentation: {e}", exc_info=True)
+        sys.exit(1)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

scripts/start_chat.py

@@ -0,0 +1,90 @@
+#!/usr/bin/env python3
+"""
+Startup script for chat service with documentation indexing.
+Runs indexing if needed, then starts the chat server.
+"""
+
+import asyncio
+import logging
+import os
+import subprocess
+import sys
+from pathlib import Path
+
+logging.basicConfig(
+    level=logging.INFO,
+    format="%(asctime)s - %(levelname)s - %(message)s"
+)
+logger = logging.getLogger(__name__)
+
+
+async def main() -> None:
+    """Main startup routine"""
+
+    logger.info("=" * 50)
+    logger.info("Datacenter Documentation Chat Service")
+    logger.info("Starting initialization...")
+    logger.info("=" * 50)
+
+    # Check if vector store needs initialization
+    vector_store_path = Path("/app/data/chroma_db")
+    index_marker = vector_store_path / ".indexed"
+
+    if not index_marker.exists():
+        logger.info("")
+        logger.info("=" * 50)
+        logger.info("First Time Setup")
+        logger.info("=" * 50)
+        logger.info("Indexing documentation into vector store...")
+        logger.info("This may take a few minutes...")
+        logger.info("")
+
+        # Run indexing script
+        try:
+            result = subprocess.run(
+                [sys.executable, "/app/scripts/index_docs.py"],
+                check=True,
+                capture_output=True,
+                text=True
+            )
+            logger.info(result.stdout)
+
+            # Create marker file
+            vector_store_path.mkdir(parents=True, exist_ok=True)
+            index_marker.touch()
+            logger.info("")
+            logger.info("✓ Documentation indexed successfully!")
+
+        except subprocess.CalledProcessError as e:
+            logger.error("")
+            logger.error(f"⚠ Warning: Documentation indexing failed: {e}")
+            logger.error(e.stdout)
+            logger.error(e.stderr)
+            logger.error("  The chat service will still start but won't have access to indexed documentation.")
+    else:
+        logger.info(f"✓ Vector store already initialized (marker: {index_marker})")
+        logger.info("  To re-index, delete the volume: docker volume rm datacenter-docs-chat-data-dev")
+
+    logger.info("")
+    logger.info("=" * 50)
+    logger.info("Starting Chat Server")
+    logger.info("=" * 50)
+    logger.info("Listening on port 8001...")
+    logger.info("")
+
+    # Start the chat server by importing and running it
+    # This keeps everything in the same process
+    os.chdir("/app")
+    sys.path.insert(0, "/app/src")
+
+    from datacenter_docs.chat import main as chat_main
+
+    # Run the chat server
+    import uvicorn
+    from datacenter_docs.chat.main import socket_app
+
+    uvicorn.run(socket_app, host="0.0.0.0", port=8001)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

scripts/start_chat.sh

@@ -0,0 +1,45 @@
+#!/bin/bash
+# Startup script for chat service with documentation indexing
+
+set -e
+
+echo "=== Datacenter Documentation Chat Service ==="
+echo "Starting initialization..."
+
+# Check if vector store needs initialization
+VECTOR_STORE_PATH="/app/data/chroma_db"
+INDEX_MARKER="$VECTOR_STORE_PATH/.indexed"
+
+if [ ! -f "$INDEX_MARKER" ]; then
+    echo ""
+    echo "=== First Time Setup ==="
+    echo "Indexing documentation into vector store..."
+    echo "This may take a few minutes..."
+    echo ""
+
+    # Run indexing script
+    python /app/scripts/index_docs.py
+
+    # Create marker file to prevent re-indexing
+    if [ $? -eq 0 ]; then
+        mkdir -p "$VECTOR_STORE_PATH"
+        touch "$INDEX_MARKER"
+        echo ""
+        echo "✓ Documentation indexed successfully!"
+    else
+        echo ""
+        echo "⚠ Warning: Documentation indexing failed. Chat will work with limited functionality."
+        echo "  The chat service will still start but won't have access to indexed documentation."
+    fi
+else
+    echo "✓ Vector store already initialized (found marker: $INDEX_MARKER)"
+    echo "  To re-index, delete the volume: docker volume rm datacenter-docs-chat-data-dev"
+fi
+
+echo ""
+echo "=== Starting Chat Server ==="
+echo "Listening on port 8001..."
+echo ""
+
+# Start the chat server
+exec python -m datacenter_docs.chat.main